| User | Pijiuhua |
| Upload Date | October 21 2025 02:17 AM |
| Views | 11 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 26.1 |
| Model | iPad Pro (12.9-inch 3rd Generation) |
| Model ID | iPad8,7 |
| Motherboard | J321AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.66 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
886
164.7 IPS |
|
|
Image Classification (HP)
|
100% |
1250
232.4 IPS |
|
|
Image Classification (Q)
|
96% |
160
29.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
358
5.80 IPS |
|
|
Image Segmentation (HP)
|
100% |
373
6.05 IPS |
|
|
Image Segmentation (Q)
|
99% |
226
3.67 IPS |
|
|
Pose Estimation (SP)
|
100% |
2817
3.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
4000
4.67 IPS |
|
|
Pose Estimation (Q)
|
96% |
1746
2.04 IPS |
|
|
Object Detection (SP)
|
100% |
909
72.1 IPS |
|
|
Object Detection (HP)
|
100% |
1214
96.3 IPS |
|
|
Object Detection (Q)
|
92% |
183
14.6 IPS |
|
|
Face Detection (SP)
|
100% |
3387
40.3 IPS |
|
|
Face Detection (HP)
|
100% |
3887
46.2 IPS |
|
|
Face Detection (Q)
|
100% |
295
3.51 IPS |
|
|
Depth Estimation (SP)
|
100% |
2929
22.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
4117
31.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
539
4.21 IPS |
|
|
Style Transfer (SP)
|
100% |
7855
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9741
12.5 IPS |
|
|
Style Transfer (Q)
|
96% |
2975
3.84 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1389
51.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1785
65.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
395
14.6 IPS |
|
|
Text Classification (SP)
|
100% |
101
134.3 IPS |
|
|
Text Classification (HP)
|
100% |
101
135.2 IPS |
|
|
Text Classification (Q)
|
93% |
103
138.0 IPS |
|
|
Machine Translation (SP)
|
100% |
527
9.07 IPS |
|
|
Machine Translation (HP)
|
100% |
494
8.50 IPS |
|
|
Machine Translation (Q)
|
98% |
472
8.16 IPS |